Year: 2002
Type: conference-paper
Abstract: We have been developing robust natural language tools for the automated extraction of structured information from biomedical texts as part of a project we call MEDSTRACT. Here we will present demonstrations of two biological literature database servers, the Bio-Relation Server and the Bio-Acronym server, Acromed, both derived automatically from robust natural language processing of Medline text. Visualization tools for navigating the databases and exploring the results of a search are also demonstrated. The presentation consists of four distinct demos over these two databases, demonstrating the extraction results, presented in both tabular form and graphically, as well as a live illustration of how the text coherence and anaphora resolution module improves overall performance of the database results.
Authors: James Pustejovsky, Brent Cochran, Jose Castaño
Institutions: Brandeis University, Tufts University
Language: English
Subfield: Molecular Biology
Domain: Life Sciences
Open Access status: bronze
OpenAlex ID: W2793356376